Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cell
    -0.07
     ACS
    -0.07
    .Field
    -0.07
    _active
    -0.06
    117
    -0.06
     Dennis
    -0.06
    ippets
    -0.06
     tiempo
    -0.06
    /info
    -0.06
     alc
    -0.06
    POSITIVE LOGITS
    /th
    0.07
    另外
    0.06
     starters
    0.06
    รอง
    0.06
    orElse
    0.06
     необ
    0.06
    ในท
    0.06
    StringLength
    0.06
    :update
    0.06
    --)
    0.06
    Act Density 0.001%

    No Known Activations